← All examples

ModelEthio-ASR Amharic (600M)0Ethio-ASR Multi (300M)1Ethio-ASR Multi (600M)2Ethio-ASR Multi (94M)2Meta MMS-1B7OmniASR-CTC (1B)5OmniASR-CTC (300M)2OmniASR-CTC (3B)1OmniASR-LLM (1B)7OmniASR-LLM (300M)1OmniASR-LLM (3B)1OpenAI Whisper-small17
Audio qualityClean Studio7Ambient Room Noise17Harsh Environment19Distant / Low-Volume Mic7Wideband Phone (VoLTE)7Randomized Phone Channel7Narrowband 2G + Packet Loss21

What did the model get wrong?

OpenAI Whisper-small Ambient Room Noise   Example 3 of 20  ·  speaker: Female

🎧 Listen — Ambient Room Noise
Realistic everyday background noise — like a normal room or café.
✅ What was actually said
በስልክ ደውየ ማግኘት የምችልበት የጥሪ ማእከል አለ
🤖 What this model heard
but the only thing that i can do is to make sure that i can eat it
Correct
Wrong (different word)
Missed (skipped)
Extra (added)
0
Correct
7
Wrong
0
Missed
10
Extra
0%
Words right
Out of 7 spoken words, this model got 0 right (0%). Errors: 7 words wrong; 10 extra.

Try switching Audio quality — see the same model degrade as the audio gets noisier.